Econometrica: Mar, 2003, Volume 71, Issue 2

A Bias–Reduced Log–Periodogram Regression Estimator for the Long–Memory Parameter

https://doi.org/10.1111/1468-0262.00420
p. 675-712

Donald W. K. Andrews, Patrik Guggenberger

In this paper, we propose a simple bias–reduced log–periodogram regression estimator, , of the long–memory parameter, , that eliminates the first– and higher–order biases of the Geweke and Porter–Hudak (1983) (GPH) estimator. The bias–reduced estimator is the same as the GPH estimator except that one includes frequencies to the power 2 for =1,…,, for some positive integer , as additional regressors in the pseudo–regression model that yields the GPH estimator. The reduction in bias is obtained using assumptions on the spectrum only in a neighborhood of the zero frequency.